Package mdp :: Package hinet :: Class CloneLayer

Class CloneLayer

Layer with a single node instance that is used multiple times.

The same single node instance is used to build the layer, so
Clonelayer(node, 3) executes in the same way as Layer([node]*3).
But Layer([node]*3) would have a problem when closing a training phase,
so one has to use CloneLayer.

A CloneLayer can be used for weight sharing in the training phase. It might
be also useful for reducing the memory footprint use during the execution
phase (since only a single node instance is needed).

Instance Methods

[hide private]

__init__(self, node, n_nodes=1, dtype=None)
Setup the layer with the given list of nodes.

_execute(self, x, *args, **kwargs)
Process the data through the internal nodes.

_inverse(self, x, *args, **kwargs)
Combine the inverse of all the internal nodes.

_stop_training(self, *args, **kwargs)
Stop training of the internal node.

execute(self, x, *args, **kwargs)
Process the data through the internal nodes.

inverse(self, x, *args, **kwargs)
Combine the inverse of all the internal nodes.

stop_training(self, *args, **kwargs)
Stop training of the internal node.

Inherited from unreachable.newobject: __long__, __native__, __nonzero__, __unicode__, next

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__, __sizeof__, __subclasshook__

Inherited from Layer

__contains__(self, item)

__getitem__(self, key)

__iter__(self)

__len__(self)

_check_props(self, dtype)
Check the compatibility of the properties of the internal nodes.

_get_output_dim_from_nodes(self)
Calculate the output_dim from the nodes and return it.

_get_supported_dtypes(self)
Return the list of dtypes supported by this node.

_get_train_seq(self)
Return the train sequence.

_pre_execution_checks(self, x)
Make sure that output_dim is set and then perform normal checks.

_set_dtype(self, t)

_train(self, x, *args, **kwargs)
Perform single training step by training the internal nodes.

is_invertible(self)
Return True if the node can be inverted, False otherwise.

is_trainable(self)
Return True if the node can be trained, False otherwise.

train(self, x, *args, **kwargs)
Perform single training step by training the internal nodes.

Inherited from Node

__add__(self, other)

__call__(self, x, *args, **kwargs)
Calling an instance of Node is equivalent to calling its execute method.

__repr__(self)
repr(x)

__str__(self)
str(x)

_check_input(self, x)

_check_output(self, y)

_check_train_args(self, x, *args, **kwargs)

_if_training_stop_training(self)

_pre_inversion_checks(self, y)
This method contains all pre-inversion checks.

_refcast(self, x)
Helper function to cast arrays to the internal dtype.

_set_input_dim(self, n)

_set_output_dim(self, n)

copy(self, protocol=None)
Return a deep copy of the node.

get_current_train_phase(self)
Return the index of the current training phase.

get_dtype(self)
Return dtype.

get_input_dim(self)
Return input dimensions.

get_output_dim(self)
Return output dimensions.

get_remaining_train_phase(self)
Return the number of training phases still to accomplish.

get_supported_dtypes(self)
Return dtypes supported by the node as a list of numpy.dtype objects.

has_multiple_training_phases(self)
Return True if the node has multiple training phases.

is_training(self)
Return True if the node is in the training phase, False otherwise.

save(self, filename, protocol=-1)
Save a pickled serialization of the node to filename. If filename is None, return a string.

set_dtype(self, t)
Set internal structures' dtype.

set_input_dim(self, n)
Set input dimensions.

set_output_dim(self, n)
Set output dimensions.

Properties

[hide private]

Inherited from object: __class__

Inherited from Node

_train_seq
List of tuples:

dtype
dtype

input_dim
Input dimensions

output_dim
Output dimensions

supported_dtypes
Supported dtypes

Method Details

[hide private]

init(self, node, n_nodes=1, dtype=None)
(Constructor)

Setup the layer with the given list of nodes.

Keyword arguments:
node -- Node to be cloned.
n_nodes -- Number of repetitions/clones of the given node.

Overrides: object.__init__

_execute(self, x, *args, **kwargs)

Process the data through the internal nodes.

Overrides: Node._execute

_inverse(self, x, *args, **kwargs)

Combine the inverse of all the internal nodes.

Overrides: Node._inverse

_stop_training(self, *args, **kwargs)

Stop training of the internal node.

Overrides: Node._stop_training

execute(self, x, *args, **kwargs)

Process the data through the internal nodes.

Overrides: Node.execute

inverse(self, x, *args, **kwargs)

Combine the inverse of all the internal nodes.

Overrides: Node.inverse

stop_training(self, *args, **kwargs)

Stop training of the internal node.

Overrides: Node.stop_training

Class CloneLayer

__init__(self, node, n_nodes=1, dtype=None) (Constructor)

_execute(self, x, *args, **kwargs)

_inverse(self, x, *args, **kwargs)

_stop_training(self, *args, **kwargs)

execute(self, x, *args, **kwargs)

inverse(self, x, *args, **kwargs)

stop_training(self, *args, **kwargs)

init(self, node, n_nodes=1, dtype=None)
(Constructor)